Characterizing Opinion Evolution of Networked LLMs
This work provides a foundational understanding of opinion propagation in multi-agent LLM systems, which is crucial for designing and regulating LLM-driven social platforms and simulations.
The authors investigate whether classical opinion dynamics models can capture the behavior of LLM networks and find that simple modifications, particularly including bias, reduce cumulative estimated mean opinion error by up to 88%.
Large language models (LLMs) increasingly interact with one another in multi-agent systems, from simulations of human discourse to influence operations and fully LLM-driven social platforms. These interactions give rise to new regimes of opinion propagation that are not yet well understood. We investigate whether classical opinion dynamics models, which have long been used to explain how interactions shape collective beliefs in human societies, can capture the behavior of LLM networks. We find that, while naive averaging-style models fail to track LLMs' opinion dynamics, simple modifications yield substantial gains in modeling fidelity. In particular, bias, an innate opinion toward which agents regress, emerges as a significant driver of LLM opinion dynamics, with its inclusion reducing cumulative estimated mean opinion error by up to 88%. We additionally find that these conclusions generalize across model families, discussion topics, and networks.